Representing Compositionality based on Multiple Timescales Gated Recurrent Neural Networks with Adaptive Temporal Hierarchy for Character-Level Language Models

Representing Compositionality based on Multiple Timescales Gated Recurrent Neural Networks with Adaptive Temporal Hierarchy for Character-Level Language Models Dennis Singh Moirangthem author Jegyung Son author Minho Lee author 2017-08 text Proceedings of the 2nd Workshop on Representation Learning for NLP Phil Blunsom editor Antoine Bordes editor Kyunghyun Cho editor Shay Cohen editor Chris Dyer editor Edward Grefenstette editor Karl Moritz Hermann editor Laura Rimell editor Jason Weston editor Scott Yih editor Association for Computational Linguistics Vancouver, Canada conference publication moirangthem-etal-2017-representing 10.18653/v1/W17-2616 https://aclanthology.org/W17-2616/ 2017-08 131 138